Yesil Science / Blog
Blog
Every article we have published: research summaries, product thinking and developments in health AI.
Latest articles

AI improves heart calcium scoring on basic scans
A new machine learning method extracts high-quality heart disease risk data from low-dose scans that doctors usually ignore for calcium scoring.

AI Outperforms Doctors on Cancer Reports
When algorithms read pathology reports better than the oncologists who ordered them, the bottleneck in cancer care shifts from diagnostic accuracy to...

Algorithms sort Parkinson’s from lookalike brain diseases
A new machine learning approach shows that while AI can easily spot the difference between Parkinson's and its deadlier lookalikes, pinpointing the...

The Health AI Brief — Week of July 6, 2026
What the First FDA-Cleared LLM Actually Does

Young people are outsourcing therapy to algorithms
When vulnerable teenagers turn to artificial intelligence for mental health advice, they are not finding a cure—they are finding a mirror that...

AI tracks sleep disorder severity using video
A new study shows video foundation models can grade violent sleep movements, but their tendency to overestimate severity reveals the limits of...

FDA Crackdown Hits Telehealth GLP-1 Sales
The wild west of online weight-loss drug marketing is officially coming to an end.

Physician epistemic framing alters the accuracy of large language models for medical second opinions
A doctor's self-doubt can degrade the accuracy of medical AI, proving that these systems are highly sensitive to how questions are framed.

Digital Twins Solve Rare Disease Trial Dilemma
Using virtual clones to simulate disease progression could finally solve the recruitment bottleneck that stalls rare disease drug development.

AI predicts kidney cancer immunotherapy survival rates
A new machine learning model uses basic blood markers to predict how kidney cancer patients respond to immunotherapy.

NHS funds ambient voice tech across hospitals
A massive funding injection promises to free doctors from keyboards, but the financial plumbing of the NHS could stall the rollout.

Digital twins predict cardiac pacing success
A new digital twin model shows that one-third of heart failure patients fail cardiac therapy because surgeons are aiming at the wrong...
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.